The lane detection is a key problem to solve the division of derivable areas in unmanned driving, and the detection accuracy of lane lines plays an important role in the decision-making of vehicle driving. Scenes faced by vehicles in daily driving are relatively complex. Bright light, insufficient light, and crowded vehicles will bring varying degrees of difficulty to lane detection. So we combine the advantages of spatial convolution in spatial information processing and the efficiency of ERFNet in semantic segmentation, propose an endto-end network to lane detection in a variety of complex scenes. And we design the information exchange block by combining spatial convolution and dilated convolution, which plays a great role in understanding detailed information. Finally, our network was tested on the CULane database and its F1-measure with IOU threshold of 0.5 can reach 71.9%.

This paper presents a neural network system where we participate in the first task of SemEval-2020 shared task 7 "Assessing the Funniness of Edited News Headlines". Our target is to create a neural network model that predicts the funniness of edited headlines. We build our model using a combination of LSTM and TF-IDF, then a feed-forward neural network. The system manages to slightly improve RSME scores regarding our mean score baseline. 1

No abstract

No abstract

Objectives: The purpose of this study was to explore the independent risk factors of chronic ventricular dilatation after aneurysmal subarachnoid haemorrhage. Methods: A retrospective study was carried out in patients with aneurysmal subarachnoid haemorrhage and admitted to the Second Affiliated Hospital of Chongqing Medical University from July 2017 to February 2021. The patients were grouped according to whether they had chronic ventricular dilatation. The patients’ demographic, clinical, and imaging datas including gender, age, hypertension, Hunt and Hess grade, Fisher grade, intraventricular hemorrhage, acute ventricular dilatation, aneurysm location, cerebrospinal fluid drainage, surgical methods, and meningitis were recorded and analyzed. And binary multivariate logistic regression models were used to investigate the independent risks for the chronic ventricular dilatation. Results: A total of 70 patients were analyzed and 36 (51.4%) developed chronic ventricular dilatation. Univariate analysis showed that age, Hunt and Hess grade, Fisher grade, intraventricular hemorrhage, acute ventricular dilatation, subtentorial aneurysms, and cerebrospinal fluid drainage were significantly different between the two groups. And there was no significant difference between the two groups in gender, hypertension, surgical method, or meningitis. Multivariate logistic regression analysis showed that acute ventricular dilatation was the only independent risk factor for chronic ventricular dilatation after aneurysmal subarachnoid haemorrhage (OR 92.1, 95% CI: 11.7–999.9, P < 0.001). Conclusions: Acute ventricular dilatation was an independent risk factor of chronic ventricular dilatation after aneurysmal subarachnoid haemorrhage. Future research is needed to assess whether early treatment of acute ventricular dilatation can reduce chronic ventricular dilatation.